A clustering-based approach for discovering interesting places in trajectories

• DOI: 10.1145/1363686.1363886
• Publication Date: 2008-04-29T13:04:11Z
• Authors: Andrey Tietbohl P...; Vania Bogorny; Bart Kuijpers; Luis Otavio Alvares
• Keywords: Sample (material)

Because of the large amount trajectory data produced by mobile devices, there is an increasing need for mechanisms to extract knowledge from this data. Most existing works have focused on geometric properties trajectories, but recently emerged concept semantic in which background geographic information integrated sample points. In new concept, trajectories are observed as a set stops and moves, where most important parts trajectory. Stops moves been computed testing intersections with objects given user. paper we present alternative solution capability finding interesting places that not expected The proposed spatio-temporal clustering method, based speed, work single trajectories. We compare two different approaches experiments real show computation using speed can be several applications.